© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9874
    Prev
    Next
    INDEX
    Explanations

    flag status state tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PUSTAKA
    -1.29
    を作り
    -1.29
    ,
    -1.29
    chränkungen
    -1.23
     In
    -1.21
     (~(
    -1.20
     cualquiera
    -1.20
     kwietnia
    -1.14
     Familienname
    -1.10
     紹介
    -1.08
    POSITIVE LOGITS
     this
    2.39
    This
    1.85
    Whether
    1.70
     cette
    1.62
    on
    1.59
     then
    1.52
     هذا
    1.48
     whether
    1.45
    phère
    1.44
    これは
    1.41
    Activations Density 0.023%

    No Known Activations